Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to storytelling and character relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressed Stacy’s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.48
    AndEndTag
    -0.43
    IUrlHelper
    -0.40
     setId
    -0.39
     archivo
    -0.38
    ARCHIVE
    -0.38
    SBATCH
    -0.37
    لينكات
    -0.37
    UnusedPrivate
    -0.36
    OrEmpty
    -0.36
    POSITIVE LOGITS
     EconPapers
    0.69
    MockBean
    0.46
     ComVisible
    0.43
    ImageContext
    0.42
    uatan
    0.41
    pośred
    0.41
     CreateTagHelper
    0.41
     linkovi
    0.41
    pexpr
    0.41
    natural
    0.40
    Act Density 0.049%

    No Known Activations